In the reconstruction of sparse signals in compressed sensing, the reconstruction algorithm is required to reconstruct the sparsest form of signal. In order to minimize the objective function, minimal norm algorithm and greedy pursuit algorithm are most commonly used. The minimum L₁ norm algorithm has very high reconstruction accuracy, but this convex optimization algorithm cannot get the sparsest signal like the minimum L₀ norm algorithm. However, because the L₀ norm method is a non-convex problem, it is difficult to get the global optimal solution and the amount of calculation required is huge. In this paper, a new algorithm is proposed to approximate the smooth L₀ norm from the approximate L₂ norm. First we set up an approximation function model of the sparse term, then the minimum value of the objective function is solved by the gradient projection, and the weight of the function model of the sparse term in the objective function is adjusted adaptively by the reconstruction error value to reconstruct the sparse signal more accurately. Compared with the pseudo inverse of L₂ norm and the L₁ norm algorithm, this new algorithm has a lower reconstruction error in one-dimensional sparse signal reconstruction. In simulation experiments of two-dimensional image signal reconstruction, the new algorithm has shorter image reconstruction time and higher image reconstruction accuracy compared with the usually used greedy algorithm and the minimum norm algorithm.

Graph convolutional networks (GCNs) have brought considerable improvement to the skeleton-based action recognition task. Existing GCN-based methods usually use the fixed spatial graph size among all the layers. It severely affects the model’s abilities to exploit the global and semantic discriminative information due to the limits of receptive fields. Furthermore, the fixed graph size would cause many redundancies in the representation of actions, which is inefficient for the model. The redundancies could also hinder the model from focusing on beneficial features. To address those issues, we proposed a plug-and-play channel adaptive merging module (CAMM) specific for the human skeleton graph, which can merge the vertices from the same part of the skeleton graph adaptively and efficiently. The merge weights are different across the channels, so every channel has its flexibility to integrate the joints. Then, we build a novel shallow graph convolutional network (SGCN) based on the module, which achieves state-of-the-art performance with less computational cost. Experimental results on NTU-RGB+D and Kinetics-Skeleton illustrates the superiority of our methods.

Neural network pruning, an important method to reduce the computational complexity of deep models, can be well applied to devices with limited resources. However, most current methods focus on some kind of information about the filter itself to prune the network, rarely exploring the relationship between the feature maps and the filters. In this paper, two novel pruning methods are proposed. First, a new pruning method is proposed, which reflects the importance of filters by exploring the information in the feature maps. Based on the premise that the more information there is, more important the feature map is, the information entropy of feature maps is used to measure information, which is used to evaluate the importance of each filter in the current layer. Further, normalization is used to realize cross layer comparison. As a result, based on the method mentioned above, the network structure is efficiently pruned while its performance is well reserved. Second, we proposed a parallel pruning method using the combination of our pruning method above and slimming pruning method which has better results in terms of computational cost. Our methods perform better in terms of accuracy, parameters, and FLOPs compared to most advanced methods. On ImageNet, it is achieved 72.02% top1 accuracy for ResNet50 with merely 11.41M parameters and 1.12B FLOPs.For DenseNet40, it is obtained 94.04% accuracy with only 0.38M parameters and 110.72M FLOPs on CIFAR10, and our parallel pruning method makes the parameters and FLOPs are just 0.37M and 100.12M, respectively, with little loss of accuracy.

Despite many years of research, the accuracy of small target detection is still restricted by the complex background. In addition, the contradiction between the computation complexity reduction and detection performance improvement makes it hard to apply some high-performance methods towards practical application. In this letter, a novel group image-patch tensor model (GIPT) is proposed to solve the above problems. Firstly, based on the structure tensor theory, a newly designed measurement criterion is employed to divide the image pixels into three types: point area, flat area, and line area. Second, image pixels with line priors and point priors are assigned to different weights to reduce the effects of strong background edges. Third, a group image-patch tensor model is proposed to better explore the low-rank of the background, in which patches with the same feature type are rearranged into the same group for tensor decomposition. Moreover, the proposed GIPT model can make the optimization process run in parallel, which can greatly reduce the complexity of the algorithms. The experiment results show the superiority of the proposed method compared with other state-of-the-art algorithms.